Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    prosecution-related terms, such as names of suspects, criminal charges, and legal actions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "of" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    attribute
    -0.78
     entit
    -0.70
    obyl
    -0.65
    TEXT
    -0.65
    âĢķ
    -0.64
     surrog
    -0.64
     disse
    -0.63
    Characters
    -0.63
     compiled
    -0.63
     substr
    -0.62
    POSITIVE LOGITS
     Pasadena
    0.98
     Queens
    0.92
     Oakland
    0.90
     Auckland
    0.87
     Antioch
    0.86
     Anaheim
    0.86
     Providence
    0.86
     Minneapolis
    0.84
     Brooklyn
    0.83
     Rochester
    0.83
    Act Density 0.056%

    No Known Activations